Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 19589
    Prev
    Next
    INDEX
    Explanations

    corrections or thought changes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,加
    -0.09
     nətic
    -0.08
     nieces
    -0.08
     weiteren
    -0.08
     andre
    -0.08
     Nein
    -0.08
     арқ
    -0.08
     aega
    -0.08
     sorgt
    -0.07
     vingers
    -0.07
    POSITIVE LOGITS
    I'll
    0.13
     I'll
    0.11
     We'll
    0.10
    We'll
    0.10
     i'll
    0.10
    represented
    0.10
     represented
    0.08
     preferably
    0.08
    Rather
    0.08
     perhaps
    0.08
    Activations Density 0.057%

    No Known Activations